{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/learning-visual-n-grams-from-web-data","title":"Learning Visual N-Grams from Web Data","arxiv_id":"1612.09161","date":"2016-12-29","proceeding":"ICCV 2017 10","authors":["Ang Li","Allan Jabri","Armand Joulin","Laurens van der Maaten"],"abstract":"Real-world image recognition systems need to recognize tens of thousands of\nclasses that constitute a plethora of visual concepts. The traditional approach\nof annotating thousands of images per class for training is infeasible in such\na scenario, prompting the use of webly supervised data. This paper explores the\ntraining of image-recognition systems on large numbers of images and associated\nuser comments. In particular, we develop visual n-gram models that can predict\narbitrary phrases that are relevant to the content of an image. Our visual\nn-gram models are feed-forward convolutional networks trained using new loss\nfunctions that are inspired by n-gram models commonly used in language\nmodeling. We demonstrate the merits of our models in phrase prediction,\nphrase-based image retrieval, relating images and captions, and zero-shot\ntransfer.","url_abs":"http://arxiv.org/abs/1612.09161v2","url_pdf":"http://arxiv.org/pdf/1612.09161v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"zero-shot-transfer-image-classification","task_name":"Zero-Shot Transfer Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-2","task":"Zero-Shot Transfer Image Classification","dataset":"SUN","model":"Visual N-Grams","rank_in_archive_order":3,"of":3,"metrics":{"Accuracy":"23.0"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on","task":"Zero-Shot Transfer Image Classification","dataset":"aYahoo","model":"Visual N-Grams","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"72.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1612.09161","atlas_url":"https://app.syntology.ai/?focus=1612.09161","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1612.09161"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1612.09161\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1612.09161"},"call":"get_concepts_for_paper(arxiv_id=\"1612.09161\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"f1cec4d9dd0fc07827c2c802c487f14acee4c3b25f3833ca1c36005f33dce0fe","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}